Skip to content

Updated Noise Eval #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
shahzeb171 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Updated Noise Eval #4

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7,474 changes: 0 additions & 7,474 deletions data/gsm/mistral/mistral_gsm_response.csv
View file
Open in desktop

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions script/gsm/flan_gsm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
from jsonformer import Jsonformer

from config import access_token, DIR_PATH
from utils import get_questions_and_answer_from_dataset
from utils import get_noisy_questions_and_answer_from_dataset

tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-xl")
model = T5ForConditionalGeneration.from_pretrained(
Expand All @@ -26,8 +26,8 @@
},
}

csv_file = f"{DIR_PATH}/data/gsm/train_preprocessed.csv"
questions, ground_truths = get_questions_and_answer_from_dataset(csv_file)
csv_file = f"{DIR_PATH}/data/noisy_datasets/gsm8k_noisy_punct_10.csv"
questions, ground_truths = get_noisy_questions_and_answer_from_dataset(csv_file)


output_file = (
Expand Down
6 changes: 3 additions & 3 deletions script/gsm/mistral_gsm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@
from jsonformer import Jsonformer

from config import access_token, DIR_PATH
from utils import get_questions_and_answer_from_dataset
from utils import get_noisy_questions_and_answer_from_dataset

access_token = access_token
model_name = "mistralai/Mistral-7B-v0.1"
Expand Down Expand Up @@ -46,8 +46,8 @@
},
}

csv_file = f"{DIR_PATH}/data/gsm/train_preprocessed.csv"
questions, ground_truths = get_questions_and_answer_from_dataset(csv_file)
csv_file = f"{DIR_PATH}/data/noisy_datasets/gsm8k_noisy_punct_10.csv"
questions, ground_truths = get_noisy_questions_and_answer_from_dataset(csv_file)


output_file = (
Expand Down
6 changes: 3 additions & 3 deletions script/gsm/mistral_instruct_gsm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@
from jsonformer import Jsonformer

from config import access_token, DIR_PATH
from utils import get_questions_and_answer_from_dataset
from utils import get_noisy_questions_and_answer_from_dataset


access_token = access_token
Expand Down Expand Up @@ -46,8 +46,8 @@
},
}

csv_file = f"{DIR_PATH}/data/gsm/train_preprocessed.csv"
questions, ground_truths = get_questions_and_answer_from_dataset(csv_file)
csv_file = f"{DIR_PATH}/data/noisy_datasets/gsm8k_noisy_punct_10.csv"
questions, ground_truths = get_noisy_questions_and_answer_from_dataset(csv_file)


output_file = f"{DIR_PATH}/data/gsm/mistral_instruct/mistral_instruct_gsm_response.csv"
Expand Down
6 changes: 3 additions & 3 deletions script/gsm/mistral_math_gsm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@
from jsonformer import Jsonformer

from config import access_token, DIR_PATH
from utils import get_questions_and_answer_from_dataset
from utils import get_noisy_questions_and_answer_from_dataset


access_token = access_token
Expand Down Expand Up @@ -45,8 +45,8 @@
},
}

csv_file = f"{DIR_PATH}/data/gsm/train_preprocessed.csv"
questions, ground_truths = get_questions_and_answer_from_dataset(csv_file)
csv_file = f"{DIR_PATH}/data/noisy_datasets/gsm8k_noisy_punct_10.csv"
questions, ground_truths = get_noisy_questions_and_answer_from_dataset(csv_file)

#TODO: Change to relative path
output_file = f"{DIR_PATH}/data/gsm/mistral_math/mistral_math_gsm_response.csv"
Expand Down
9 changes: 9 additions & 0 deletions script/gsm/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -78,3 +78,12 @@ def safe_convert_llm_to_int(value):
)

print("Accuracy saved to accuracy.csv.")



def get_noisy_questions_and_answer_from_dataset(csv_file_path):
# Load the specific CSV file
data = pd.read_csv(csv_file_path)
questions = data["noisy_questions"].tolist()
groundTruths = data["numeric_answer"].tolist()
return questions,groundTruths